SR-LLM: An incremental symbolic regression framework driven by LLM-based retrieval-augmented generation
Proceedings of the National Academy of Sciences · 30.12.2025 · 122 (52)
DOI: 10.1073/pnas.2516995122 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 22.12.2025. Verfasst von Zelin Guo und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Automation, Tsinghua University, Beijing 100084, China. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Symbolic regression (SR) has regained research prominence as deep learning advancements accelerate the search for analytical models from observational data. However, the vast search space often hinders existing algorithms to yield complex analytical expressions. We present SR-LLM, an SR framework integrating retrieval-augmented generation mechanisms based on large language models (LLM) to achieve incremental learning. Specifically, our framework is capable of leveraging accumulated prior knowledge and past exploration results from external knowledge bases to retrieve the most relevant information for current regression tasks. It first composes prior information into small symbolic groups with the assistance of the LLMs and then utilizes deep reinforcement learning to combine these groups to formulate complex yet explainable analytic expressions that are more easily understood by humans. The capability for efficient knowledge utilization enables our framework to integrate all previous human experiences and exploration results, effectively learning by standing on the shoulders of giants. To validate the effectiveness of our proposed method, we not only test the framework on popular symbolic regression benchmarks but also extend its application to a domain where the explicit optimal model remains controversial: how to analytically describe human car-following behavior based on observed vehicle trajectories? Experiments confirm that our method outperforms on standard benchmarks, successfully rediscovers famous traditional car-following models and discovers new models from empirical trajectory data, achieving both fitting effectiveness and interpretability.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Automation, Tsinghua University, Beijing 100084, China.
- State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China.
- SCAN Center, University of Glasgow, Glasgow, G12 8QB, United Kingdom.
- Department of Engineering, University of Cambridge, Cambridge, CB2 1PZ, United Kingdom.
- John von Neumann Faculty of Informatics, Obuda University, Budapest H-1034, Hungary.
- Department of Electrical Engineering Systems, University of Southern California, Los Angeles, CA 90007.
ORCID-Profile: Zelin Guo, Siqi Wang, Yonglin Tian, Jing Yang, Hui Yu, Levente Kovács, Li Li, Fei-Yue Wang
Zitieren
APA
Guo, Z., Wang, S., Tian, Y., Yang, J., Yu, H., Na, X., Kovács, L., Li, L., Ioannou, P. A., & Wang, F. Y. (2025). SR-LLM: An incremental symbolic regression framework driven by LLM-based retrieval-augmented generation. Proceedings of the National Academy of Sciences, 122(52). https://doi.org/10.1073/pnas.2516995122
Vancouver
Guo Z, Wang S, Tian Y, Yang J, Yu H, Na X, et al. SR-LLM: An incremental symbolic regression framework driven by LLM-based retrieval-augmented generation. Proceedings of the National Academy of Sciences. 2025;122(52). doi:10.1073/pnas.2516995122
BibTeX
@article{Guo2025,
author = {Guo, Zelin and Wang, Siqi and Tian, Yonglin and Yang, Jing and Yu, Hui and Na, Xiaoxiang and Kovács, Levente and Li, Li and Ioannou, Petros A and Wang, Fei-Yue},
title = {SR-LLM: An incremental symbolic regression framework driven by LLM-based retrieval-augmented generation},
journal = {Proceedings of the National Academy of Sciences},
year = {2025},
volume = {122},
number = {52},
doi = {10.1073/pnas.2516995122}
}
EUVIMED